> ## Documentation Index > Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt > Use this file to discover all available pages before exploring further. # Build a Prompt > Learn what prompts are, how to build, test, improve, and save versioned prompts in Arize AX's Prompt Hub. ## What are prompts? A **prompt** is the instruction set you send to an LLM. In Arize, a prompt is managed as a **Prompt Object**: messages, model settings, tools/functions, and response format together as one versioned artifact. Diagram of a Prompt Object including template messages, parameters, tools, and response format System, user, and assistant messages with variables like `{customer_input}`. Model choice and invocation parameters such as temperature and max tokens. Optional tool definitions and function-calling behavior. Output schema and structure your application expects. Prompt editor showing system and user messages with a highlighted template variable where input data is injected ## Build and improve a prompt Start in **Playground** with a draft prompt, then refine it for clarity, correctness, and brevity. ### Create a prompt Navigate to Playgrounds and click New Playground, or start from the home page and have Alyx create a playground Navigate to **Playgrounds** and click **New Playground** to create a new playground. You can also start from the home page, and **Alyx** will create a playground for you. If you have not already added one, select your LLM provider and model in the Playground before you draft or run. Options include OpenAI, Azure, Vertex AI, AWS Bedrock, and others. LLM provider and model dropdowns in the Prompt Playground Describe your use case in plain language in the **Alyx** panel on the right. Include details about what your prompt should capture, desired output format, tone, length, etc. **Alyx** will wire them in automatically. For example, you could say: > Create a prompt for a customer support agent that handles returns and escalations. Use `{customer_input}` and `{order_id}` as variables. Give feedback on Alyx's drafts and keep iterating until you are satisfied with the prompt. If you added a dataset or test cases, **run the prompt** over rows to check outputs. If you skipped that step, exercise the prompt with manual inputs or keep iterating with Alyx. For a fuller testing workflow, see [**Test a prompt**](#test-a-prompt). Navigate to **Playgrounds** and click **New Playground** to create a new playground. Select your LLM provider and model from OpenAI, Azure, Vertex AI, AWS Bedrock, and others. LLM provider and model dropdowns in the Prompt Playground Add any system, user, or assistant messages. Use curly braces around names (for example, `{destination}`) for template variables filled dynamically at run time. Click **Functions** and paste tool definitions as JSON. Function descriptions must be in JSON format. To add multiple functions, add entries to the JSON list with the proper attributes. Set **Function Selection** to give the model instructions on when to invoke each function. Adding function definitions and function selection in the Prompt Playground Click **Params** to configure temperature, max completion tokens, frequency penalty, and more. Different LLM providers expose different hyperparameters that affect the output. Create a prompt and initial version from code. Use the reference for your stack: Full options (providers, invocation params, tools): [Create a Prompt](/api-clients/python/version-8/client-resources/prompts#create-a-prompt) in the Python v8 Prompts API. ```python theme={null} from arize._generated.api_client.models.input_variable_format import InputVariableFormat from arize._generated.api_client.models.llm_provider import LlmProvider from arize._generated.api_client.models.llm_message import LLMMessage prompt = client.prompts.create( space="your-space-name-or-id", name="customer-support-agent", description="Handles returns and escalations", commit_message="Initial version", input_variable_format=InputVariableFormat.F_STRING, provider=LlmProvider.OPENAI, model="gpt-4o", messages=[ LLMMessage(role="system", content="You are a support agent for {company}."), LLMMessage(role="user", content="{ticket_text}"), ], ) print(prompt.id, prompt.name) ``` Full options: [Create a Prompt](/api-clients/typescript/version-1/client-resources/prompts#create-a-prompt) in the TypeScript Prompts API. ```typescript theme={null} import { createPrompt } from "@arizeai/ax-client"; const prompt = await createPrompt({ space: "my-space", name: "customer-support", description: "Handles returns and escalations", version: { commitMessage: "Initial version", inputVariableFormat: "f_string", provider: "openAI", model: "gpt-4o", messages: [ { role: "system", content: "You are a support agent for {company_name}." }, { role: "user", content: "{ticket_text}" }, ], }, }); ``` Flags and message JSON shape: [`ax prompts create`](/api-clients/cli/prompts#ax-prompts-create) in the CLI reference. ```bash theme={null} ax prompts create \ --name "customer-support-agent" \ --space sp_abc123 \ --provider openAI \ --input-variable-format f_string \ --messages '[{"role":"system","content":"You are a support agent for {company}."},{"role":"user","content":"{ticket_text}"}]' \ --model gpt-4o \ --description "Handles returns and escalations" \ --commit-message "Initial version" ``` ### Test a prompt Test your prompt against real examples before shipping.